Presented By: DCMB Seminar Series
DCMB / CCMB Weekly Seminar Series
Craig Galban, PhD (Director of Preclinical Imaging & Computational Analysis, Rogel Cancer Center; Professor, Radiology; Adjunct Professor, Biomedical Engineering; Affiliate Faculty Member of CCMB)
Talk title: Clinical Trajectory analysis to determine risk-factors of Copd: A COPDGene Study
Abstract:
Background
Chronic obstructive pulmonary disease (COPD) presents significant clinical heterogeneity and a wide variety of progression trajectories [1]. Clinical trajectory analysis (ClinTrajAn) is a powerful tool based on elastic principal graphs for the calculation of trajectories from large cross-sectional clinical data sets [2].
Aims and objectives
Our objective was to determine potential risk-factors by evaluate progression trajectories in COPD using ClinTrajAn on the COPDGene Phase I (baseline visit) dataset.
Methods
7883 participants, current and former smokers with GOLD 0 thru 4 COPD, from Phase I of the COPDGene study, were utilized for this work. 55 features were obtained for each subject, including demographics, spirometry, smoking history and computed tomography (CT), which included Parametric Response Mapping (PRM). Developed by our group, PRM is capable of simultaneously measuring small airways disease and emphysema which are the main contributors of airflow limitations in COPD. The resulting data matrix was analyzed with ClinTrajAn.
Results
A principal tree, with 13 branch segments and 8 termini, was generated (Figure 1). There was a clearly recognized trajectory from healthier subjects through decreasing lung function and increasing age (Figure 1 A), increasing in GOLD (Figure 1 B), to an emphysema high terminus (Figure 1 C). Notably this method illustrated numerous branching points along this trajectory.
Conclusions
In this study we used ClinTrajAn to obtain a map of disease progression trajectories in COPD including clinically recognized pathogenesis. Our next steps will be to further validate this approach using longitudinal data from the COPDGene follow-up visits.
References
1. Han MK, Agusti A, Calverley PM, Celli BR, Criner G, Curtis JL, Fabbri LM, Goldin JG, Jones PW, MacNee W, Make BJ. Chronic obstructive pulmonary disease phenotypes: the future of COPD. American journal of respiratory and critical care medicine. 2010 Sep 1;182(5):598-604.
2. Golovenkin SE, Bac J, Chervov A, Mirkes EM, Orlova YV, Barillot E, Gorban AN, Zinovyev A. Trajectories, bifurcations, and pseudo-time in large clinical datasets: applications to myocardial infarction and diabetes data. GigaScience. 2020 Nov;9(11):giaa128.
Zoom link: https://umich-health.zoom.us/j/93929606089?pwd=SHh6R1FOQm8xMThRemdxTEFMWWpVdz09
Abstract:
Background
Chronic obstructive pulmonary disease (COPD) presents significant clinical heterogeneity and a wide variety of progression trajectories [1]. Clinical trajectory analysis (ClinTrajAn) is a powerful tool based on elastic principal graphs for the calculation of trajectories from large cross-sectional clinical data sets [2].
Aims and objectives
Our objective was to determine potential risk-factors by evaluate progression trajectories in COPD using ClinTrajAn on the COPDGene Phase I (baseline visit) dataset.
Methods
7883 participants, current and former smokers with GOLD 0 thru 4 COPD, from Phase I of the COPDGene study, were utilized for this work. 55 features were obtained for each subject, including demographics, spirometry, smoking history and computed tomography (CT), which included Parametric Response Mapping (PRM). Developed by our group, PRM is capable of simultaneously measuring small airways disease and emphysema which are the main contributors of airflow limitations in COPD. The resulting data matrix was analyzed with ClinTrajAn.
Results
A principal tree, with 13 branch segments and 8 termini, was generated (Figure 1). There was a clearly recognized trajectory from healthier subjects through decreasing lung function and increasing age (Figure 1 A), increasing in GOLD (Figure 1 B), to an emphysema high terminus (Figure 1 C). Notably this method illustrated numerous branching points along this trajectory.
Conclusions
In this study we used ClinTrajAn to obtain a map of disease progression trajectories in COPD including clinically recognized pathogenesis. Our next steps will be to further validate this approach using longitudinal data from the COPDGene follow-up visits.
References
1. Han MK, Agusti A, Calverley PM, Celli BR, Criner G, Curtis JL, Fabbri LM, Goldin JG, Jones PW, MacNee W, Make BJ. Chronic obstructive pulmonary disease phenotypes: the future of COPD. American journal of respiratory and critical care medicine. 2010 Sep 1;182(5):598-604.
2. Golovenkin SE, Bac J, Chervov A, Mirkes EM, Orlova YV, Barillot E, Gorban AN, Zinovyev A. Trajectories, bifurcations, and pseudo-time in large clinical datasets: applications to myocardial infarction and diabetes data. GigaScience. 2020 Nov;9(11):giaa128.
Zoom link: https://umich-health.zoom.us/j/93929606089?pwd=SHh6R1FOQm8xMThRemdxTEFMWWpVdz09
Related Links
Explore Similar Events
-
Loading Similar Events...
